Efficient Drug-Pathway Association Analysis via Integrative Penalized Matrix Decomposition

Abstract

Traditional drug discovery practice usually follows the “one drug – one target” approach, seeking to identify drug molecules that act on individual targets, which ignores the systemic nature of human diseases. Pathway-based drug discovery recently emerged as an appealing approach to overcome this limitation. An important first step of such pathway-based drug discovery is to identify associations between drug molecules and biological pathways. This task has been made feasible by the accumulating data from high-throughput transcription and drug sensitivity profiling. In this paper, we developed “iPaD”, an integrative Penalized Matrix Decomposition method to identify drug-pathway associations through jointly modeling of such high-throughput transcription and drug sensitivity data. A scalable bi-convex optimization algorithm was implemented and gave iPaD tremendous advantage in computational efficiency over current state-of-the-art method, which allows it to handle the ever-growing large-scale data sets that current method cannot afford to. On two widely used real data sets, iPaD also significantly outperformed the current method in terms of the number of validated drug-pathway associations that were identified. The Matlab code of our algorithm publicly available at http://licong-jason.github.io/iPaD/

Identifying drug-pathway association pairs based on L1L2,1-integrative penalized matrix decomposition

“…But for our method and the -iPaD method, 53 drug-pathway association pairs are identified, with 16 association pairs validated in the CancerResource database. In addition, in [ 8 ], we can easily find that the results of iFad and GSEA methods are poorer than the iPaD method, so in this paper, we does not compare our method with the iFad and GSEA methods.…”

“…Compared with the “one drug-one target” methods, the systematic biology approach takes the drug effects into the global physiological environment account [ 6 ]. These existing computational methods for identifying drug targets include the Gene Set Enrichment Analysis (GSEA) method [ 7 ], the FacPad method [ 2 ], the iFad method [ 5 ] and the iPaD method [ 8 ], etc. The GSEA method has several disadvantages.…”

“…Also it has many turning parameters which should be specified by users. In order to improve the algorithm speed and performance, a method named iPaD (integrative Penalized Matrix Decomposition) is proposed by Li et al[ 8 ] to identify paired drug-pathway associations. The iPaD method applies the integrative penalized matrix decomposition method to analyze the gene expression data and the drug sensitivity data.…”

“…Since the -norm penalty can produce sparsity, the -norm regularization item is added on the drug-pathway association matrix. By applying the iPaD method on the NCI-60 and Cancer Cell Line Encyclopedia (CCLE) datasets, Li et al [ 8 ] prove that the iPaD method performs better than the iFad method in computational efficiency and identifying drug-pathway association pairs. Since the -norm regularization can penalize each row of the matrix as a whole and can enhance the sparsity among the rows [ 11 ], based on this theory, a method named -iPaD ( -integrative Penalized Matrix Decomposition) is proposed to identify paired drug-pathway associations [ 12 ].…”

“…In fact, the CCLE data set in the CCLE project contains 18988 genes and 24 chemical drugs. The detailed data processing can be found in [ 8 ]. The drug sensitivities are measured by area over the dose-response curve (‘activity area’).…”